A typed-decision layer for Google's DiffusionGemma, from David Villalón at Maisa AI. It compiles a request into a small answer canvas, runs one denoising read on patched vLLM and reads the probabilities of the allowed labels, for text, images and images offered as options.
An embedding model turned decision model. Qwen3-Embedding-4B with a merged LoRA, driven by the open JevEmbed toolkit, which scores Choice, Score and Noul questions from embedding similarity and returns a distribution without generating text.
Decides
choice, score, noul
choice, score, noul, classify
Architecture
djev
jevembed
Fine-tuned from
google/diffusiongemma-26b-a4b-it
qwen/qwen3-embedding-4b
License
apache-2.0
apache-2.0
Availability
Open weights + hosted API
Open weights
Hosted by
Maisa
—
Input price
$0.035/MTok
—
Decision accuracy
—
85.9%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
p95 latency
—
—
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between djev and jevembed?
djev is from Maisa and jevembed from HIT-TMG (Lychee Team). djev has open weights and a hosted API; jevembed has open weights you can download and run. Both answer choice, score and noul questions. Only jevembed answers classify. jevembed is the smaller model, at 4.0B parameters to 26B.
Which is more accurate, djev or jevembed?
Only jevembed publishes an accuracy figure (85.9% on JevEmbed-Data test split (64,110 hard-label questions), final LoRA checkpoint before merging); djev does not, so there is no comparison to make without your own test.
Which is cheaper, djev or jevembed?
djev: $0.035 / $0 per 1M, or free to self-host. jevembed: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run djev or jevembed locally?
Yes, both: systemone pull maisa/djev and systemone pull hit-tmg/jevembed download the weights.
Evaluation suite
—
JevEmbed-Data test split (64,110 hard-label questions), final LoRA checkpoint before merging